© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14156
    Prev
    Next
    INDEX
    Explanations

    on an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /on
    -0.14
    /from
    -0.13
    /out
    -0.12
    lest
    -0.10
    acs
    -0.10
    oled
    -0.10
    curring
    -0.10
    jury
    -0.09
     regards
    -0.09
    wards
    -0.09
    POSITIVE LOGITS
    iano
    0.10
     )"
    0.09
     REC
    0.09
    onis
    0.08
    ÑĥÑĩ
    0.08
    /***
    0.08
    ylim
    0.08
    ’y
    0.08
    abant
    0.07
    ief
    0.07
    Activations Density 0.057%

    No Known Activations